Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes
Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes
复制标题
基于深度学习的设备指纹识别可提高 LoRa-IoT 安全性：对网络部署变化的敏感性
DOI：
10.1109/mnet.001.2100553
复制
发表时间：
2022
期刊：
影响因子：
9.3
通讯作者：
Abdurrahman Elmaghbub
中科院分区：
文献类型：
--
作者：
B. Hamdaoui;Abdurrahman Elmaghbub
基于深度学习的设备指纹识别最近被视为自动化网络访问认证的关键使能技术。由于复制物理特征本身具有困难，它对模拟攻击具有鲁棒性，这使其有别于传统的密码学解决方案。尽管设备指纹识别已显示出良好的性能，但其对网络操作环境变化的敏感性仍然是一个主要限制。本文提出了一个实验框架，旨在研究并克服支持LoRa的设备指纹识别对这类变化的敏感性。我们首先描述使用我们支持LoRa的无线设备测试平台收集的射频数据集。然后我们提出一种新的指纹识别技术，该技术利用由硬件损伤导致的带外失真信息来提高指纹识别的准确性。最后，我们通过实验研究和分析支持LoRa的射频指纹识别对各种网络设置变化的敏感性。我们的结果表明，当学习模型在相同设置下进行训练和测试时，指纹识别效果相对较好。然而，当在不同设置下进行训练和测试时，当使用IQ数据作为输入时，这些模型对信道条件变化表现出中等敏感性，对协议配置和接收器硬件变化表现出严重敏感性。然而，当使用FFT数据作为输入时，它们在任何变化下表现都不佳。
Deep-learning-based device fingerprinting has recently been recognized as a key enabler for automated network access authentication. Its robustness to impersonation attacks due to the inherent difficulty of replicating physical features is what distinguishes it from conventional cryptographic solutions. Although device fingerprinting has shown promising performance, its sensitivity to changes in the network operating environment still poses a major limitation. This article presents an experimental framework that aims to study and overcome the sensitivity of LoRa-enabled device fingerprinting to such changes. We first begin by describing RF datasets we collected using our LoRa-enabled wireless device testbed. We then propose a new fingerprinting technique that exploits out-of-band distortion information caused by hardware impairments to increase the fingerprinting accuracy. Finally, we experimentally study and analyze the sensitivity of LoRa RF finger-printing to various network setting changes. Our results show that fingerprinting does relatively well when the learning models are trained and tested under the same settings. However, when trained and tested under different settings, these models exhibit moderate sensitivity to channel condition changes and severe sensitivity to protocol configuration and receiver hardware changes when IQ data is used as input. However, when FFT data is used as input, they perform poorly under any change.
影响因子：
9.3
作者：
Hamdaoui, Bechir;Elmaghbub, Abdurrahman;Mejri, Siefeddine
通讯作者：
Mejri, Siefeddine
全面的射频数据集收集和发布：基于深度学习的设备指纹识别用例
DOI：
10.1109/gcwkshps52748.2021.9682024
发表时间：
2021
期刊：
2020 IEEE Global Communications Conference
影响因子：
--
作者：
Elmaghbub, Abdurrahman;Hamdaoui, Bechir
通讯作者：
Hamdaoui, Bechir
WideScan：利用深度学习的带外失真进行设备分类
DOI：
10.1109/globecom42002.2020.9348138
发表时间：
2020
期刊：
2020 IEEE Global Communications Conference
影响因子：
--
作者：
Elmaghbub, Abdurrahman;Hamdaoui, Bechir;Natarajan, Arun
通讯作者：
Natarajan, Arun